Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Simple_Unsupervised_Keyphrase_Extraction_using_...

Avatar for MARUYAMA MARUYAMA
May 02, 2019
0
190

 Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf

Avatar for MARUYAMA

MARUYAMA

May 02, 2019
Tweet

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
Avatar for MARUYAMA tmaru0204
0
180
Misspelling_Oblivious_Word_Embedding.pdf
Avatar for MARUYAMA tmaru0204
0
190
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
Avatar for MARUYAMA tmaru0204
0
180
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
160
20191028_literature-review.pdf
Avatar for MARUYAMA tmaru0204
0
150
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
140
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
Avatar for MARUYAMA tmaru0204
0
170
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
Avatar for MARUYAMA tmaru0204
0
150
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
150

Featured

See All Featured
Principles of Awesome APIs and How to Build Them.
Avatar for Keavy McMinn keavy
126
17k
Scaling GitHub
Avatar for Zach Holman holman
463
140k
GitHub's CSS Performance
Avatar for Jon Rohan jonrohan
1032
460k
Documentation Writing (for coders)
Avatar for Carmen Chung carmenintech
74
5k
Keith and Marios Guide to Fast Websites
Avatar for Keith Pitt keithpitt
411
22k
Into the Great Unknown - MozCon
Avatar for Noah Learner thekraken
40
2k
Typedesign – Prime Four
Avatar for Hannes Fritz hannesfritz
42
2.8k
Embracing the Ebb and Flow
Avatar for Simon Collison colly
87
4.8k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
180
9.9k
Code Review Best Practice
Avatar for Trisha Gee trishagee
71
19k
GraphQLとの向き合い方2022年版
Avatar for Yosuke Kurami quramy
49
14k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
Avatar for mongodb mongodb
48
9.7k

Transcript

  1. 4JNQMF6OTVQFSWJTFE,FZQISBTF&YUSBDUJPO VTJOH4FOUFODF&NCFEEJOHT ,BNJM#FOOBOJ4NJSFT $MBVEJV.VTBU "OESFBB)PTTNBOO .JDIBFM#BFSJTXZM .BSUJO+BHHJ $P/-- QQ -JUFSBUVSFSFWJFX

    /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB

  2. "CTUSBDU ⾣'TDPSFʹ͓͍ͯطଘख๏Λ্ճΔੑೳΛୡ੒ ⾣4FOUFODFFNCFEEJOHʹΑΔڭࢣͳ͠ख๏ΛఏҊ &NCFE3BOL ⾣4VQFSWJTFELFZQISBTFFYUSBDUJPO ɾΞϊςʔγϣϯ͞Εͨେن໛ͳίʔύε͕ඞཁ ɾυϝΠϯ֎ͷೖྗʹऑ͍

  3. &NCFE3BOL ⾣ҎԼͷTUFQͰ࣮ߦ  ඼ࢺʹج͍ͮͯɺจॻ͔ΒϑϨʔζΛநग़  จॻͱϑϨʔζΛಉۭؒ͡ʹຒΊࠐΈ ɾ%PDWFD &NCFE3BOLEW ɾ4FOUWFD &NCFE3BOLTW

     จॻϕΫτϧʹ͍ۙϕΫτϧΛ࣋ͭϑϨʔζΛநग़ ɾ$PTJOFTJNJMBSJUZ

  4. &NCFE3BOL NPMFDVMBSFRVJWBMFODFJOEJDFT NPMFDVMBSFRVJWBMFODFOVNCFS NPMFDVMBSFRVJWBMFODFOVNCFST UPQPMPHJDBMTIBQFT UPQPMPHJDBMTIBQF நग़͞ΕͨΩʔϑϨʔζʹ৑௕ੑ͕͋Δ

  5. &NCFE3BOL ⾣&NCFE3BOL ީิͷଟ༷ੑΛߟྀ &NCFE3BOL  ඼ࢺʹج͍ͮͯɺจॻ͔ΒϑϨʔζΛநग़  จॻͱϑϨʔζΛಉۭؒ͡ʹຒΊࠐΈ ɾ4FOUWFD &NCFE3BOL

    TW  จॻϕΫτϧʹ͍ۙϕΫτϧΛ࣋ͭϑϨʔζΛநग़ ɾ.BYJNBM.BSHJOBM3FMFWBODF

  6. &NCFE3BOL ⾣.BYJNBM.BSHJOBM3FMFWBODF ..3 $ΩʔϑϨʔζͷީิͱͳΔϑϨʔζͷू߹ ,நग़͞ΕͨΩʔϑϨʔζू߹ EPDจॻϕΫτϧ $J $KϑϨʔζͷϕΫτϧ

  7. &NCFE3BOL ⾣/PSNBMJ[FEDPTJOFTJNJMBSJUZ М ɾ ඪ४ภࠩ

  8. &NCFE3BOL

  9. &YQFSJNFOUTFUUJOH ⾣%BUBTFUT ɾ*OTQFDTDJFOUJpDKPVSOBMBCTUSBDUT ୹͍จॻ ɾ%6$OFXTQBQFSBSUJDMF தఔ౓ͷ௕͞ͷจॻ ɾ/64GVMMTDJFOUJpDDPOGFSFODFQBQFST ௕͍จॻ 3FDBMM͸ෆՄೳ

  10. 3FTVMUT &NCFE3BOL͸ɺ *OTQFDɾ%6$ʹ͓͍ͯ طଘख๏Λ্ճΔੑೳ /64ʹ͓͍ͯ͸ɺ 5PQJD3BOL .VMUJQBSUJUF ͕ߴ͍είΞΛه࿥ ௕͍จॻͰ͸ɺ จॻ಺ʹ͓͚Δ

    ϑϨʔζͷग़ݱҐஔͷ ৘ใ͕ॏཁ

  11. 3FTVMUT &NCFE3BOLʹ QPTJUJPOBMCJBTΛՃ͑ %6$ /64ʹ͓͚Δ ɹੑೳΛվળ

  12. 3FTVMUT &NCFE3BOLͷํ͕ &NCFE3BOL ΑΓ΋ ߴ͍'TDPSFΛ֫ಘ

  13. 3FTVMUT ⾣ਓखධՁ ɾ*OTQFD %6$ͷจॻ ɾྑ͍ΩʔϑϨʔζू߹ʹ౤ථ Е&NCFE3BOL Е&NCFE3BOL

  14. $PODMVTJPO ⾣'TDPSFධՁʹؔ͢Δ໰୊Λࢦఠ ⾣4FOUFODFFNCFEEJOHʹΑΔڭࢣͳ͠ख๏ΛఏҊ &NCFE3BOL ɾൺֱత୹͍จॻ *OTQFD %6$ ʹ͓͍ͯޮՌత ɾྨࣅͨ͠,FZQISBTF্͕ҐΛ઎Ίͯ͠·͏ ⾣,FZQISBTFͷଟ༷ੑΛߟྀ

    &NCFE3BOL ɾϢʔβʹΑΔධՁͰ͸ɺ&NCFE3BOLʹൺ΂ߴ͍ධՁΛ֫ಘ